diff --git a/neon2rvv.h b/neon2rvv.h
index e4241800..9bd6570b 100644
--- a/neon2rvv.h
+++ b/neon2rvv.h
@@ -2783,7 +2783,15 @@ FORCE_INLINE int8x8x2_t vld2_s8(const int8_t *__a) { return __riscv_vlseg2e8_v_i
 
 // FORCE_INLINE uint32x4x2_t vld2q_u32(const uint32_t *__a);
 
-// FORCE_INLINE int8x8x2_t vld2_lane_s8(const int8_t *__a, int8x8x2_t __b, const int __c);
+FORCE_INLINE int8x8x2_t vld2_lane_s8(const int8_t *__a, int8x8x2_t __b, const int __c) {
+  const uint8_t mask_arr[] = {(uint8_t)(1 << __c)};
+  vbool8_t mask = __riscv_vlm_v_b8(mask_arr, 1);
+  vint8m1_t a_dup0 = vdup_n_s8(__a[0]);
+  vint8m1_t a_dup1 = vdup_n_s8(__a[1]);
+  vint8m1_t c0 = __riscv_vmerge_vvm_i8m1(__riscv_vget_v_i8m1x2_i8m1(__b, 0), a_dup0, mask, 8);
+  vint8m1_t c1 = __riscv_vmerge_vvm_i8m1(__riscv_vget_v_i8m1x2_i8m1(__b, 1), a_dup1, mask, 8);
+  return __riscv_vcreate_v_i8m1x2(c0, c1);
+}
 
 // FORCE_INLINE int16x4x2_t vld2_lane_s16(const int16_t *__a, int16x4x2_t __b, const int __c);
 
diff --git a/tests/impl.cpp b/tests/impl.cpp
index 8434d750..736bcb41 100644
--- a/tests/impl.cpp
+++ b/tests/impl.cpp
@@ -3666,7 +3666,54 @@ result_t test_vld2q_u16(const NEON2RVV_TEST_IMPL &impl, uint32_t iter) { return
 
 result_t test_vld2q_u32(const NEON2RVV_TEST_IMPL &impl, uint32_t iter) { return TEST_UNIMPL; }
 
-result_t test_vld2_lane_s8(const NEON2RVV_TEST_IMPL &impl, uint32_t iter) { return TEST_UNIMPL; }
+result_t test_vld2_lane_s8(const NEON2RVV_TEST_IMPL &impl, uint32_t iter) {
+  const int8_t *_a = (int8_t *)impl.test_cases_int_pointer1;
+  const int8_t *_b = (int8_t *)impl.test_cases_int_pointer2;
+  int8x8x2_t c;
+  int8x8x2_t b = vld2_s8(_b);
+  c = vld2_lane_s8(_a, b, 0);
+  if (TEST_FAIL == validate_int8(c, _a[0], _b[2], _b[4], _b[6], _b[8], _b[10], _b[12], _b[14], _a[1], _b[3], _b[5],
+                                 _b[7], _b[9], _b[11], _b[13], _b[15])) {
+    return TEST_FAIL;
+  }
+  c = vld2_lane_s8(_a, b, 1);
+  if (TEST_FAIL == validate_int8(c, _b[0], _a[0], _b[4], _b[6], _b[8], _b[10], _b[12], _b[14], _b[1], _a[1], _b[5],
+                                 _b[7], _b[9], _b[11], _b[13], _b[15])) {
+    return TEST_FAIL;
+  }
+  c = vld2_lane_s8(_a, b, 2);
+  if (TEST_FAIL == validate_int8(c, _b[0], _b[2], _a[0], _b[6], _b[8], _b[10], _b[12], _b[14], _b[1], _b[3], _a[1],
+                                 _b[7], _b[9], _b[11], _b[13], _b[15])) {
+    return TEST_FAIL;
+  }
+  c = vld2_lane_s8(_a, b, 3);
+  if (TEST_FAIL == validate_int8(c, _b[0], _b[2], _b[4], _a[0], _b[8], _b[10], _b[12], _b[14], _b[1], _b[3], _b[5],
+                                 _a[1], _b[9], _b[11], _b[13], _b[15])) {
+    return TEST_FAIL;
+  }
+  c = vld2_lane_s8(_a, b, 4);
+  if (TEST_FAIL == validate_int8(c, _b[0], _b[2], _b[4], _b[6], _a[0], _b[10], _b[12], _b[14], _b[1], _b[3], _b[5],
+                                 _b[7], _a[1], _b[11], _b[13], _b[15])) {
+    return TEST_FAIL;
+  }
+  c = vld2_lane_s8(_a, b, 5);
+  if (TEST_FAIL == validate_int8(c, _b[0], _b[2], _b[4], _b[6], _b[8], _a[0], _b[12], _b[14], _b[1], _b[3], _b[5],
+                                 _b[7], _b[9], _a[1], _b[13], _b[15])) {
+    return TEST_FAIL;
+  }
+  c = vld2_lane_s8(_a, b, 6);
+  if (TEST_FAIL == validate_int8(c, _b[0], _b[2], _b[4], _b[6], _b[8], _b[10], _a[0], _b[14], _b[1], _b[3], _b[5],
+                                 _b[7], _b[9], _b[11], _a[1], _b[15])) {
+    return TEST_FAIL;
+  }
+  c = vld2_lane_s8(_a, b, 7);
+  if (TEST_FAIL == validate_int8(c, _b[0], _b[2], _b[4], _b[6], _b[8], _b[10], _b[12], _a[0], _b[1], _b[3], _b[5],
+                                 _b[7], _b[9], _b[11], _b[13], _a[1])) {
+    return TEST_FAIL;
+  }
+
+  return TEST_SUCCESS;
+}
 
 result_t test_vld2_lane_s16(const NEON2RVV_TEST_IMPL &impl, uint32_t iter) { return TEST_UNIMPL; }